© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 9-GEMMASCOPE-2-RES-262K
    7. 11347
    Prev
    Next
    INDEX
    Explanations

    gr8 b8 m8 i r8 8/8

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_9_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     dona
    1.45
     RIP
    1.40
    ECTOR
    1.39
     yrs
    1.31
    蓣
    1.29
     kneading
    1.28
     replicates
    1.27
     bereaved
    1.27
     [],
    1.26
    
    1.24
    POSITIVE LOGITS
    ла
    1.53
    ک
    1.49
    ła
    1.49
    ات
    1.47
    ণ
    1.37
    絣
    1.35
    in
    1.27
    ով
    1.25
    Equation
    1.22
     aquele
    1.22
    Activations Density 0.001%

    No Known Activations